What is the context window of Codestral 2508 by NanoGPT?

Codestral 2508 by NanoGPT has a context window of 256K tokens. It supports up to 256K input tokens and can generate up to 33K output tokens.

What input and output types does Codestral 2508 support?

Codestral 2508 by NanoGPT accepts text as input and can generate text as output.

Is Codestral 2508 by NanoGPT open source?

No, Codestral 2508 by NanoGPT has closed weights. The model is only available through the NanoGPT API.

Back to Models

Codestral 2508 API

NanoGPT

About

Process massive datasets with Codestral 2508, featuring an expansive 256K context window for long-document analysis. This model delivers cost-effective pricing at $0.30/1M input and $0.90/1M output tokens. Access Codestral 2508 via the NanoGPT API with up to 33K output tokens.

Capabilities

Input Modalities

text

Output Modalities

text

Reasoning

Structured Output

Tool Use

WeightsClosed

Temperature

Fixed

Attachment

Not Supported

Limits

Context Window

256K

Tokens

Input Limit

256K

Tokens

Max Output

33K

Tokens

Pricing

Standard (per 1M tokens)

Input

$0.30

Output

$0.90

Frequently Asked Questions

Codestral 2508 by NanoGPT costs $0.30 per 1M input tokens and $0.90 per 1M output tokens.

Model Details

mistralai/codestral-2508

Provider

NanoGPT

Family

codestral

Release Date

Aug 1, 2025

Knowledge Cutoff

N/A

API Integration

NPM Package

@ai-sdk/openai-compatible

Environment Variables

NANO_GPT_API_KEY

API Base URL

https://nano-gpt.com/api/v1

Documentation